No abstract

Breast Cancer is the most dominant cause of mortality in women. Early diagnosis and treatment of the disease can stop the spreading of cancer in the breast. Due to this nature of the problem, accurate prediction is the most important measure of the predictive model. This paper proposes the comparison of ensemble learning techniques in predicting breast cancer. Ensemble learning is widely used for performance improvement of the predictive task. The ensembles algorithms used in this research study are AdaBoost, Random Forest, and XGBoost with data from Wisconsin hospitals. The result indicates that the random forest is the best predictive model for this dataset. The model has the following performance measure, accuracy 97%, sensitivity 96%, and specificity 96%. The experiment is executed using scikit-learn machine learning library. With this high level of accuracy offered by the model, the model can help the doctor to identify whether the patient has malignant or benign tumor cancer cells with high precision.

No abstract

The merge of urbanization in Indonesia results in a sharp increase in household energy consumption. Energy conservation is a global challenge for both individuals and decision-makers. The increasing household energy consumption is mostly caused by unwanted usage of electrical energy. The purpose of this paper is to design an improved smart home electricity management system based on consumer behaviour, which will help household occupant to control the usage of electricity automatic using sensor and manual using a smartphone. The sensor used in the system are a motion sensor, temperature sensor, sound sensor, and light sensor also wireless technology is used for controlling electricity outside of the home using a smartphone. The proposed system has multiple benefits of saving electricity bill of the house and keep the owner of the house updated about home security with the ability to control the home appliances and reduce electrical energy consumption.

This paper aims to model and simulate washing machine based on user expert knowledge using fuzzy logic. Fuzzy logic inference process to control washing machine in this study use Mamdani method. The method has four steps Fuzzification of linguistic variable, rule evaluation (based on expert experience), aggregation of the rules outputs and final defuzzification. Input linguistic variable used are dirtiness of the clothes, type of fabric, type of dirt and amount of the clothes and the output variable is washing time, washing speed, water intake and water temperature. The system is designed and simulated using Fuzzy logic toolbox on MATLAB. Result show that the washing machine inference relate to user expert perception. The main advantage of using fuzzy logic in washing machine is that it reduce water and electricity consumption also good time management.